KR20230052014A - Method and apparatus for classifying foreign matter - Google Patents

Abstract

A method and a device for selecting foreign substances are disclosed. The method for selecting foreign substances according to an embodiment of the present disclosure comprises the steps of: acquiring an entire image including an object to be selected and performing preprocessing to distinguish a background and the object to be selected from the entire image; detecting color information for each pixel based on a color space of the preprocessed image; calculating a color range corresponding to a normal object based on color information for each detected pixel; and determining whether there is a foreign substance in the object image according to a result of comparing the color information for each pixel based on the calculated color range.

Description

Method and apparatus for screening foreign substances {METHOD AND APPARATUS FOR CLASSIFYING FOREIGN MATTER}

The present disclosure relates to a foreign material sorting method and apparatus for calculating a color range capable of classifying a normal object and a foreign material by detecting color information in an image in which the object is photographed when detecting a foreign material in an object.

A color sorter (color sorter) is a device that sorts objects (products) by color, and can filter out foreign substances (defective goods containing foreign substances) excluding normal objects (good goods) in the sorting process. Such a color sorter can generally recognize all raw materials except for a predetermined color as defective through a color recognition detector (sensor).

That is, the color sorter classifies normal objects and foreign substances based on passive color information (color information arbitrarily designated by the user), and sets a prior art threshold of 1 degree for detecting foreign substances based on color information, and then sets the threshold value. It is disclosed about detecting foreign matter based on the value.

As such, conventional color information-based foreign material detection techniques have been able to detect a corresponding object only when a user sets a threshold value to focus on a specific object.

However, there is a problem in that color sorting is not performed properly when a foreign substance is to be detected for an object whose color variation is large depending on the production environment or for which it is difficult to limit the color of a normal object to a certain range, such as, for example, sweet potato sticks. That is, in the case of sweet potato sticks, since they have various colors depending on various environmental influences such as harvest time and place of sweet potato, which is the main material, even sweet potato sticks produced in the same process have different colors.

Therefore, when foreign matter is detected based on passive color information like a conventional color sorter, sweet potato sticks having different color information may not operate normally, and there is a problem in that the accuracy of the sorting result is reduced.

The foregoing background art is technical information that the inventor possessed for derivation of the present invention or acquired during the derivation process of the present invention, and cannot necessarily be said to be known art disclosed to the general public prior to filing the present invention.

Prior Art 1: Korean Patent Registration No. 10-1751681 (registered on June 22, 2017)

An object of an embodiment of the present disclosure is to calculate a color range capable of classifying a normal object and a foreign material by detecting color information for each pixel in an image of a photographed object when detecting a foreign material in an object, and based on the calculated color range It is to perform foreign matter detection.

The purpose of the embodiments of the present disclosure is not limited to the above-mentioned tasks, and other objects and advantages of the present invention not mentioned above can be understood by the following description and will be more clearly understood by the embodiments of the present invention. will be. It will also be seen that the objects and advantages of the present invention may be realized by means of the instrumentalities and combinations indicated in the claims.

A foreign material screening method according to an embodiment of the present disclosure includes obtaining an entire image including a target object to be screened, performing preprocessing to distinguish a background and an object to be screened from the entire image, and Detecting color information for each pixel based on a color space, calculating a color range corresponding to a normal object based on the detected color information for each pixel, and based on the calculated color range A step of determining whether there is a foreign substance in the object image according to a result of comparison with color information for each pixel may be included.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to an embodiment of the present disclosure, when detecting a foreign substance in an object, color information for each pixel is detected in an image of the object, and a color range capable of classifying a normal object and a foreign substance is calculated, and the foreign substance is based on the calculated color range. By performing the detection, the accuracy of foreign matter detection can be improved regardless of the various color ranges of the object.

In addition, by detecting the normal color range of an object in real time rather than passive color information to select foreign substances, it is possible to detect foreign substances with high performance at a relatively low cost in detecting foreign substances in objects having various colors. there is.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically illustrating a foreign material screening system environment according to an embodiment of the present disclosure.
2 is an exemplary view of a sweet potato stick image according to an embodiment of the present disclosure.
3 is a block diagram schematically illustrating a foreign material sorting apparatus according to an embodiment of the present disclosure.
4 is an exemplary diagram for explaining a pre-processing process of a sweet potato stick image according to an embodiment of the present disclosure.
5 is an exemplary diagram for explaining an HSV conversion process of a sweet potato stick image according to an embodiment of the present disclosure.
6 is an exemplary view showing a foreign material screening result of a sweet potato stick image according to an embodiment of the present disclosure.
7 is a flowchart illustrating a foreign material screening method according to an embodiment of the present disclosure.

Advantages and features of the present invention, and methods for achieving them will become clear with reference to the detailed description of embodiments in conjunction with the accompanying drawings.

However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in a variety of different forms, and includes all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the invention to which the present invention belongs. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded. Terms such as first and second may be used to describe various components, but components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. In the description with reference to the accompanying drawings, the same or corresponding components are assigned the same reference numerals, and overlapping descriptions thereof are omitted. I'm going to do it.

1 is a diagram schematically illustrating a foreign material sorting system environment according to an embodiment of the present disclosure, and FIG. 2 is an exemplary view of a sweet potato stick image according to an embodiment of the present disclosure.

Referring to FIG. 1 , the foreign material sorting system 1 of this embodiment may include a foreign material sorting device 100 , a user terminal 200 , a server 300 and a network 400 .

The foreign matter sorting system 1 of an embodiment, when detecting a foreign matter in an object, detects color information for each pixel in an image of the object, calculates a color range capable of classifying a normal object and foreign matter, and calculates the color range. It relates to performing foreign material detection based on the present invention.

In particular, in one embodiment, for objects to be detected foreign matter, it is not an object having a similar color on average, but an object that can have various colors due to the influence of the object's production process, etc. Hereinafter, sweet potato sticks It will be described as an example.

In the case of sweet potato sticks, since they have various colors depending on various environmental influences such as harvest time and place of sweet potato, which is the main material, even sweet potato sticks produced in the same process have different colors.

Generally, in the case of a color sorter that classifies grains and foreign matters, grains and foreign matters are classified based on passive color information (color information arbitrarily designated by a user). However, as shown in FIG. 2 , sweet potato sticks having different color information may not operate normally when foreign matter is classified based on passive color information.

Therefore, in one embodiment, sweet potato sticks and foreign substances can be distinguished based on color information of an image obtained in real time, rather than passive color information of sweet potato sticks.

In one embodiment, the foreign matter sorting apparatus 100 includes a chamber, lighting, machine vision, a monitor, and a warning light, and may be configured to move an object to sort foreign matter through a conveyor belt. The chamber is for machine vision to minimize the influence of the external environment, and can be used to indicate foreign matter using a monitor and a warning light so that a manager can be notified. A monitor and a warning light may be included in the user interface 120 (see FIG. 3) described below.

In one embodiment, the sweet potato sticks are separated individually and moved through a conveyor belt, and pass through the foreign matter sorting device 100 during the moving process.

That is, in one embodiment, when passing through the foreign matter sorting device 100, an image of a sweet potato stick photographed using machine vision is obtained, and a color range of the sweet potato stick is detected in this image, and foreign matter is sorted out based on this . A detailed description of the foreign material selection process will be described later.

Meanwhile, in one embodiment, users access an application or website implemented in the user terminal 200, input an image of a target object for screening foreign substances, remove foreign substances according to a result of screening foreign substances, or check a result of screening foreign substances. and so on can be performed. The user terminal 200 may receive a foreign material sorting service through an authentication process after accessing a foreign material sorting application or a foreign material sorting website. The authentication process may include authentication of inputting user information such as membership registration, authentication of a user terminal, etc., but is not limited thereto, and only accessing a link transmitted from the foreign substance sorting device 100 and/or the server 300 The authentication process may be performed as Also, in this embodiment, the user may mean a user who performs tasks such as sorting foreign substances in food in the food manufacturing step.

In one embodiment, the user terminal 200 is a desktop computer operated by a user, a smart phone, a laptop computer, a tablet PC, a smart TV, a mobile phone, a personal digital assistant (PDA), a laptop, a media player, a micro server, a global GPS (GPS). positioning system) device, e-reader, digital broadcast terminal, navigation, kiosk, MP3 player, digital camera, home appliance, and other mobile or non-mobile computing device, but is not limited thereto. In addition, the user terminal 200 may be a wearable terminal such as a watch, glasses, hair band, and ring having a communication function and a data processing function. The user terminal 200 is not limited to the above, and a terminal capable of web browsing may be borrowed without limitation.

In addition, in one embodiment, the foreign material sorting device 100 may be implemented as an internal component of a product production device or a product inspection device, or may be partially or entirely implemented as the server 300 in another embodiment.

When implemented as the server 300, images captured by product production equipment, product inspection equipment, etc., or a result of selecting foreign substances are transmitted to the server 300, and the server 300 detects color information from the captured images, Based on the color information, foreign matter can be sorted or the foreign matter sorting result can be modified. The following embodiments will be described on the premise that the foreign matter sorting device is implemented as an internal component 100 of a product production device or a product inspection device.

In one embodiment, the server 300 may be a server for operating the foreign material sorting system 1 including the foreign material sorting apparatus 100 or a server implementing part or all of the foreign material sorting apparatus 100.

In one embodiment, the server 300 photographs an object for which foreign substances are to be screened, detects color information from the captured image, and classifies a normal object and a foreign substance based on the detected color information to select foreign substances from the object. It may be a server that controls the operation of the foreign matter sorting device 100 for the overall process.

Also, the server 300 may be a database server that provides data for operating the foreign material sorting device 100 . In addition, the server 300 may include a web server, an application server, or a deep learning network providing server.

In addition, the server 300 may include a big data server and an AI server required to apply various artificial intelligence algorithms, a calculation server that performs calculations of various algorithms, and the like.

Also, in this embodiment, the server 300 may include the aforementioned servers or network with these servers.

In the foreign material sorting system 1 , the foreign material sorting device 100 and the server 300 may be connected by a network 400 . Such a network 400 may be wired networks such as LANs (local area networks), WANs (wide area networks), MANs (metropolitan area networks), ISDNs (integrated service digital networks), wireless LANs, CDMA, Bluetooth, satellite communication However, the scope of the present invention is not limited thereto. In addition, the network 400 may transmit and receive information using short-range communication and/or long-distance communication.

Also, the network 400 may include connections of network elements such as hubs, bridges, routers, switches, and gateways. Network 400 may include one or more connected networks, such as a multiple network environment, including a public network such as the Internet and a private network such as a secure corporate private network. Access to network 400 may be provided through one or more wired or wireless access networks. Furthermore, the network 400 may support an Internet of Things (IoT) network and/or 5G communication in which information is exchanged and processed between distributed components such as things.

3 is a block diagram schematically illustrating a foreign material sorting apparatus according to an embodiment of the present disclosure, FIG. 4 is an exemplary diagram for explaining a preprocessing process of a sweet potato stick image according to an embodiment of the present disclosure, and FIG. 5 is 6 is an exemplary diagram illustrating a process of HSV conversion of sweet potato stick images according to an embodiment of the present disclosure, and FIG.

Referring to FIG. 3 , the foreign material sorting apparatus 100 may include a communication unit 110 , a user interface 120 , a memory 130 and a processor 140 .

The communication unit 110 may provide a communication interface required to provide a transmission/reception signal between external devices in the form of packet data in conjunction with the network 400 . In addition, the communication unit 110 may be a device including hardware and software necessary for transmitting and receiving signals such as control signals or data signals to and from other network devices through wired or wireless connections.

That is, the processor 140 may receive various data or information from an external device connected through the communication unit 110 and may transmit various data or information to the external device.

In one embodiment, the user interface 120 is a user request for controlling the operation of the foreign matter sorting apparatus 100 (eg, changing parameters of a color space conversion algorithm, adjusting weights for calculating a color range based on a photographing environment, etc.) and an input interface through which commands are input.

And, in one embodiment, the user interface 120 may include an output interface for outputting results of foreign substance screening and the like. That is, the user interface 120 may output results according to user requests and commands. An input interface and an output interface of the user interface 120 may be implemented in the same interface.

The memory 130 may store various information necessary for the operation of the foreign material sorting apparatus 100 and/or control (operation) of the server 300 and store control software, and may include a volatile or non-volatile recording medium. can

The memory 130 is connected to one or more processors 140 and, when executed by the processor 140, causes the processor 140 to control the foreign material sorting device 100 and/or the server 300 ( cause) codes can be saved.

Here, the memory 130 may include non-temporary storage media such as magnetic storage media or flash storage media, or temporary storage media such as RAM, but the scope of the present invention is not limited thereto. The memory 130 may include built-in memory and/or external memory, and may include volatile memory such as DRAM, SRAM, or SDRAM, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, Non-volatile memory such as NAND flash memory, or NOR flash memory, SSD. It may include a compact flash (CF) card, a flash drive such as an SD card, a Micro-SD card, a Mini-SD card, an Xd card, or a memory stick, or a storage device such as an HDD. Also, information related to an algorithm for performing learning according to the present disclosure may be stored in the memory 130 . In addition, various information necessary within the scope of achieving the object of the present disclosure may be stored in the memory 130, and the information stored in the memory 130 may be updated as received from a server or an external device or input by a user. may be

The processor 140 may control the overall operation of the foreign material sorting apparatus 100 . Specifically, the processor 140 is connected to the configuration of the foreign material sorting apparatus 100 including the memory 130, and executes at least one command stored in the memory 130 to perform the overall operation of the foreign material sorting apparatus 100. can be controlled with

In one embodiment, the processor 140 obtains an RGB image having a red, green, blue (RGB) color space as shown in FIG. 4(a) using machine vision. The acquired RGB image may include an object (sweet potato stick), a foreign substance (if a foreign substance exists), and a background (conveyor belt).

Meanwhile, a color space is a concept of a space in which a color system is expressed in three dimensions, and all colors of the color display system are represented by three-dimensional coordinates in this color space.

The RGB color space expresses colors in an additive mixing method in which brightness increases when colors are mixed. The three primary colors of RGB additive mixing mean red, green, and blue. The RGB color space specifies colors based on the brightness of three channels corresponding to the three primary colors. The RGB color space is the basic principle of color representation on the web.

After acquiring the RGB image, the processor 140 may perform image preprocessing to separate the object from the background.

That is, the processor 140 may generate a mask image as shown in FIG. 4(c) by performing binarization on the acquired RGB image to remove the background. The background of the RGB image obtained using machine vision is a conveyor belt used for transporting sweet potato sticks, and it is assumed that white color is used for the conveyor belt due to the nature of the food process. Therefore, since the white conveyor belt has a high color value due to its characteristics, the background and the object can be distinguished through Equation 1 below.

Here, Tr is an average value of gray values of colors measured on an empty conveyor belt, and g(x,y) may represent a gray value of image coordinates (x,y).

In this case, in one embodiment, the processor 140 may apply blur processing as shown in FIG. 4(b) when it is determined that noise may occur in the acquired RGB image. However, depending on embodiments, applying blur processing may be omitted.

That is, pixels of an image acquired through machine vision have RGB (Red, Green, Blue) 3-channel values. However, since various foreign substances included in the sweet potato stick have various characteristics such as thickness and light transmission as well as color, in one embodiment, the processor 140, as shown in FIG. An RGB color space, which is color information, may be converted into a Hue, Saturation, Value (HSV) color space through Equation 2 below.

Here, the HSV color space may be referred to as an HSV color space or a HSV color model, and is a method of expressing colors and a method of arranging colors according to the method. A specific color is specified using the coordinates of Hue, Saturation, and Value. The color value H means a relative arrangement angle when 0° is set to red having the longest wavelength on the color wheel in which the visible light spectrum is arranged in a ring shape. Because of this, H values range from 0° to 360°, with 360° and 0° pointing to the same color red.

The saturation value S represents the degree of deepness when the deepest state of a specific color is 100%. A saturation value of 0% represents an achromatic color with the same brightness. In addition, the brightness value V represents the degree of brightness when white, red, etc. are 100% and black is 0%.

In one embodiment, in the HSV color space, as shown in FIGS. 5(b), 5(c), and 5(d), as channel images for each of Hue, Saturation, and Value It can be converted, and the ranges set for each of these hue, saturation, and lightness can operate independently without affecting each other.

Then, the processor 140 calculates an average of pixel values for each of the separated H, S, and V channels. In this case, the average of pixel values means an average value of pixels for each channel in an area excluding the background. That is, in one embodiment, since the processor 140 recognizes the average value of pixels for each channel, it is possible to obtain an average HSV value of sweet potato sticks present in the currently obtained image. This can be expressed as Equation 3 below.

와 같이 표현할 수 있다.And, in one embodiment, the HSV value per pixel of the object included in the image is

can be expressed as

In an embodiment, by comparing the HSV average value of the entire image excluding the background with the HSV value of each pixel, how much the corresponding pixel differs from the average value can be known. This can be expressed as in Equation 4 below.

Here, w represents a weight, and a weight (w) value of 1 can be used by default. However, in one embodiment, when a pixel value needs to be adjusted according to an environment for an image, such as an environment for capturing an image, the weight may be adjusted. For example, if the image is bright, the weight can be set to less than 1, and if the image is dark, it can be set to greater than 1. For example, the weight may be mainly adjusted by an environment changed by lighting, and the environment changed by lighting may include not only brightness but also saturation, color, and lightness corresponding to HSV.

In one embodiment, the weight may be adjusted by the user. For example, if it is determined that the foreign object screening environment is composed of a blackout curtain and there is little or no interference of lighting under the user's judgment, the weight may be set to 1. On the other hand, if the environment changes drastically, such as when the lighting brightens and then darkens, the HSV value can be partially adjusted by setting weights according to the environment.

In another embodiment, when a sensor capable of predicting an image environment is provided, the image environment may be automatically recognized and the weight may be adjusted. For example, by installing an illuminance sensor, a change in illuminance can be frequently sensed and a weight can be applied.

Next, the processor 140 calculates the average of the deviations (the difference between the average HSV value of the entire image excluding the background and the HSV value of each pixel) using Equation 5 to determine the average value of the deviations of the pixels of the object.

In other words, first, the processor 140 may obtain a vector distance between the entire image (the HSV average value of the entire image) and the deviation of the ith pixel using the respective H, S, and V channel values. For example, the processor 140 calculates the difference between the average value of all images in the H channel and the ith pixel, the difference value between the average value of all images in the S channel and the ith pixel, and the average value of all images in the V channel. The difference value of the i-th pixel can be obtained. That is, when the difference between the HSV vector value of the entire image and the HSV vector value of the ith pixel is obtained, a total of three HSV vector values are obtained.

At this time, the processor 140 may obtain the HSV vector distance by using the L2 Norm of the three vectors at the same rate, for example. Therefore, referring to Equation 5, a total of j+1 vector distance values of the entire image and the ith pixel can be obtained, and an average can be obtained. In one embodiment, the average may be used as a criterion for classifying regions suspected of being foreign objects and sweet potato sticks.

That is, in an embodiment, the HSV range of normal sweet potato sticks can be determined by comparing the distance between a specific pixel and the average (average of deviations of object pixels) based on the average deviation of object pixels.

Therefore, the processor 140 may determine that the sweet potato stick is normal if the average distance (average of deviations of pixels of the object) from a specific pixel of the object is closer than the average distance of deviations of all pixels of the object, and conversely, it is far. It can be classified as a foreign substance. This can be expressed as a formula as shown in Equation 6 below.

That is, the processor 140 may select foreign substances included in the sweet potato stick using Equation 6, which may output a result as shown in FIG. 6(a).

However, in one embodiment, referring to FIG. 6 (a), not only the foreign matter screening result, but also the outline of the sweet potato stick may be extracted together. This is because the contour of the sweet potato stick is thinner than the central portion and thus is greatly affected by lighting, but the area occupied by the sweet potato stick is not large, so it can be detected together as a foreign substance.

Accordingly, in one embodiment, the processor 140 may select the foreign material and then detect the outline of the object from the image obtained from machine vision. For example, in one embodiment, the background of the RGB image obtained using machine vision is a conveyor belt used for transporting sweet potato sticks, and since the conveyor belt assumes that white is used due to the nature of the food process, the background information can be said to know

Accordingly, in one embodiment, since the background information is known, it is possible to distinguish the background and the foreground (sweet potato sticks), so the background and the foreground can be binarized. Then, if the boundary of the binarized area is connected, the contour can be detected.

However, in one embodiment, a method of detecting the contour of an object is not limited thereto, and various contour detection algorithms may be employed.

After detecting the contour, the processor 140 may exclude the contour image from the image including the foreign matter and the contour. As a result, as shown in FIG. 6 (b), the problem of the boundary surface of the sweet potato stick being extracted with foreign substances is solved, and only foreign substances can be extracted as a result.

Also, when a foreign substance is found, the processor 140 may display an alarm or a screen (user interface) so that an operator can know it, or may automatically remove an object in which a foreign substance is detected according to an embodiment. If foreign substances are not detected at this time, the work can be started again from the beginning.

As described above, in the related art, the HSV value range of a normal product is obtained in advance and set in advance, and when the HSV value per pixel of an object has a HSV value within the preset range, it is determined to be a normal product. However, objects of various colors, such as sweet potato sticks, are highly likely to have different HSV values even though they are normal sweet potato sticks, and thus it is difficult to classify objects by specifying HSV values in advance. Therefore, in one embodiment, sweet potato sticks and foreign substances are distinguished based on the color information of the image obtained in real time.

7 is a flowchart illustrating a foreign material screening method according to an embodiment of the present disclosure. Referring to FIG. 7 , a series of processes of detecting color information from an object, identifying a color range of a normal object based on the color information, and selecting a foreign substance based on the identified color range will be described.

In step S100, the processor 140 acquires the entire image including the object to be sorted.

In step S200, the processor 140 performs preprocessing for distinguishing the background and the object to be selected from the entire image.

At this time, the processor 140 may obtain a background image, obtain a gray value measured for each pixel in the background image, and calculate an average value of gray values of each pixel of the background image. This process may be set and input prior to preprocessing, that is, before an image is obtained for object selection, but may be included in the preprocessing process according to embodiments.

The processor 140 may perform binarization based on a result of comparing the average value of grayscale values of each pixel of the background image with each pixel of the entire image. Also, the processor 140 may remove noise from the entire image before performing binarization, for example, may perform blur processing, but this may be omitted according to embodiments.

In step S300, the processor 140 detects color information for each pixel based on the color space of the preprocessed image.

The processor 140 obtains RGB (Red, Green, Blue) values for each pixel of the target object region in the entire image. In addition, based on a preset color space conversion algorithm, RGB values for each pixel of the target object region may be converted into Hue, Saturation, Value (HSV) values.

In this case, the preset color space conversion algorithm may be set to convert RGB values of each pixel of the object region to be screened into hue, saturation, and brightness values, respectively (see Equation 2). .

In step S400, the processor 140 calculates a color range corresponding to a normal object based on the detected color information for each pixel.

The processor 140 may calculate the HSV average value of all pixels of the entire image excluding the background, compare the HSV average value of all pixels with the HSV value of each pixel of the entire image excluding the background, and calculate the deviation. Also, the processor 140 may calculate an average value of the deviations and set them to a color range corresponding to a normal object.

In this case, the processor 140 may adjust weights for calculating the color range based on the entire image capturing environment, detect brightness of the entire image capturing environment, and adjust weights according to the detected brightness.

In step S500, the processor 140 determines whether there is a foreign substance in the object image according to the result of comparing the color information for each pixel based on the calculated color range (normal object color range).

The processor 140 may compare a deviation between the HSV value of a specific pixel and an average HSV value of all pixels in the entire image and an average value of deviations of a color range corresponding to a normal object. As a result of the comparison, the processor 140 may determine that the object is a normal object if the deviation between the HSV value of a specific pixel and the average HSV value of all pixels in the entire image is less than or equal to the normal color range value, and otherwise determine it as a foreign substance.

Also, if it is determined that there is a foreign substance in the object image, the processor 140 may detect the contour of the corresponding object image and then remove the detected contour.

In step S600, the processor 140 outputs the foreign matter determination result.

That is, the processor 140 may output a final image obtained by detecting and removing the outline as a foreign matter determination result. In other words, only the selected foreign material image can be extracted and output. However, according to an embodiment, the image of the foreign substance and the image of the object in which the foreign substance is detected may be output together.

Such processor 140 may be implemented in various ways. For example, the processor 140 may include an application specific integrated circuit (ASIC), an embedded processor, a microprocessor, hardware control logic, a hardware finite state machine (FSM), a digital signal processor Processor, DSP) may be implemented as at least one.

The processor 140, as a kind of central processing unit, may control the entire operation of the foreign material sorting apparatus 100 by driving control software loaded in the memory 130. The processor 140 may include any type of device capable of processing data. Here, a 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform functions expressed by codes or instructions included in a program, for example.

Embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed on a computer through various components, and such a computer program may be recorded on a computer-readable medium. At this time, the medium is a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a ROM hardware devices specially configured to store and execute program instructions, such as RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art in the field of computer software. Examples of computer programs may include not only machine language codes generated by a compiler but also high-level language codes that can be executed by a computer using an interpreter or the like.

In the specification of the present invention (particularly in the claims), the use of the term "above" and similar indicating terms may correspond to both singular and plural. In addition, when a range is described in the present invention, it includes an invention in which individual values belonging to the range are applied (unless there is a description to the contrary), and each individual value constituting the range is described in the detailed description of the invention Same as

The steps constituting the method according to the present invention may be performed in any suitable order unless an order is explicitly stated or stated to the contrary. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is simply to explain the present invention in detail, and the scope of the present invention is limited due to the examples or exemplary terms unless limited by the claims. it is not going to be In addition, those skilled in the art can appreciate that various modifications, combinations and changes can be made according to design conditions and factors within the scope of the appended claims or equivalents thereof.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments and should not be determined, and all scopes equivalent to or equivalently changed from the claims as well as the claims described below are within the scope of the spirit of the present invention. will be said to belong to

1: Foreign matter screening system
100: foreign matter sorting device
110: Communication Department
120: user interface
130: memory
140: processor
200: user terminal
300: server
400: Network

Claims (20)

A foreign material screening method in which at least a part of each step is performed by a processor,
acquiring an entire image including the object to be sorted, and performing preprocessing for distinguishing the object from the background in the entire image;
detecting color information for each pixel based on a color space of the preprocessed image;
calculating a color range corresponding to a normal object based on the detected color information for each pixel; and
Determining whether there is a foreign substance in the object image according to the result of comparing the color information for each pixel based on the calculated color range,
Foreign material screening method.
According to claim 1,
obtaining a background image and a gray value measured for each pixel in the background image before performing the preprocessing; and
Calculating an average grayscale value of each pixel of the background image;
Performing the preprocessing step,
Performing binarization based on a result of comparing the grayscale average value of each pixel of the background image with each pixel of the entire image,
Foreign material screening method.
According to claim 2,
Performing the preprocessing step,
Before the step of performing the binarization, further comprising removing noise from the entire image,
Foreign material screening method.
According to claim 1,
In the step of detecting color information for each pixel,
acquiring red, green, and blue (RGB) values for each pixel of the target object region in the entire image; and
Converting RGB values of each pixel of the target object region to HSV (Hue, Saturation, Value) values based on a preset color space conversion algorithm.
Foreign material screening method.
According to claim 4,
The preset color space conversion algorithm,
Based on Equation 1 below, RGB values for each pixel of the object region to be sorted are set to be converted into Hue values, Saturation values, and Value values, respectively.
Foreign material screening method.
Equation 1

According to claim 4,
Calculating the color range corresponding to the normal object,
Calculating an average HSV value of all pixels of the entire image excluding the background;
calculating a deviation by comparing the average HSV value of all pixels with the HSV value of each pixel of the entire image excluding the background; and
Comprising the step of calculating the average value of the deviation and setting it as a color range corresponding to the normal object,
Foreign material screening method.
According to claim 6,
Calculating the color range corresponding to the normal object,
Adjusting weights for color range calculation based on the entire image capturing environment,
Foreign material screening method.
According to claim 7,
In the step of adjusting the weight,
detecting the brightness of the entire image capturing environment; and
Including the step of adjusting the weight according to the detected brightness,
Foreign material screening method.
According to claim 6,
The step of determining whether or not there is a foreign substance in the object image,
comparing a deviation between an HSV value of a specific pixel and an average HSV value of all pixels in the entire image and an average value of deviations of a color range corresponding to the normal object; and
As a result of the comparison, if the deviation between the HSV value of a specific pixel and the average HSV value of all the pixels in the entire image is less than or equal to the normal color range value, determining the object as a normal object, otherwise determining it as a foreign substance.
Foreign material screening method.
According to claim 1,
detecting an outline of the corresponding object image when it is determined that there is a foreign substance in the object image; and
Further comprising the step of removing the detected contour,
Foreign material screening method.
A computer-readable recording medium having recorded thereon a program that, when executed by at least one processor, causes the at least one processor to perform the method of any one of claims 1 to 10.
As a foreign matter screening device,
a memory storing at least one instruction; and
Including at least one processor for executing the command in conjunction with the memory,
When the instruction is executed by the processor, it causes the processor to:
Obtaining an entire image including a target object to be sorted, and performing preprocessing for distinguishing the background and the object to be sorted in the entire image;
Detecting color information for each pixel based on a color space of the preprocessed image;
Based on the detected color information for each pixel, a color range corresponding to a normal object is calculated;
Based on the calculated color range, it is set to determine whether or not there is a foreign substance in the object image according to the result of comparing the color information for each pixel.
Foreign matter sorting device.
According to claim 12,
When the instruction is executed by the processor, it causes the processor to:
Before performing the preprocessing, obtaining a background image to obtain a gray value measured for each pixel in the background image;
It is set to calculate the grayscale average value of each pixel of the background image,
Set to perform preprocessing by performing binarization based on a result of comparing the grayscale average value of each pixel of the background image with each pixel of the entire image,
Foreign matter sorting device.
According to claim 12,
When the instruction is executed by the processor, it causes the processor to:
Obtaining RGB (Red, Green, Blue) values for each pixel of the object region to be sorted in the entire image;
Based on a preset color space conversion algorithm, RGB values for each pixel of the target object region are converted to HSV (Hue, Saturation, Value) values to detect color information for each pixel.
Foreign matter sorting device.
15. The method of claim 14,
The preset color space conversion algorithm,
Based on Equation 1 below, RGB values for each pixel of the object region to be sorted are set to be converted into Hue values, Saturation values, and Value values, respectively.
Foreign matter sorting device.
Equation 1

15. The method of claim 14,
When the instruction is executed by the processor, it causes the processor to:
Calculate the HSV average value of all pixels of the entire image excluding the background;
Comparing the HSV average value of all the pixels with the HSV value of each pixel of the entire image excluding the background to calculate a deviation;
Set to determine the color range corresponding to the normal object by calculating the average value of the deviation,
Foreign matter sorting device.
17. The method of claim 16,
When the instruction is executed by the processor, it causes the processor to:
When calculating the color range corresponding to the normal object, it is set to adjust the weight for calculating the color range based on the entire image shooting environment,
Foreign matter sorting device.
18. The method of claim 17,
When the instruction is executed by the processor, it causes the processor to:
Detecting the brightness of the entire image capturing environment when adjusting the weights;
Set to adjust the weight according to the detected brightness,
Foreign matter sorting device.
17. The method of claim 16,
When the instruction is executed by the processor, it causes the processor to:
Comparing a deviation between the HSV value of a specific pixel in the entire image and an average HSV value of all pixels, and an average value of deviations of a color range corresponding to the normal object;
As a result of the comparison, if the deviation between the HSV value of a specific pixel and the average HSV value of all pixels in the entire image is less than or equal to the normal color range value, it is determined as a normal object, and otherwise determined as a foreign substance.
Foreign matter sorting device.
According to claim 12,
When the instruction is executed by the processor, it causes the processor to:
If it is determined that there is a foreign substance in the object image, detecting the contour of the object image,
Set to remove the detected contour,
Foreign matter sorting device.

Images